MOESM3 of Old drug repositioning and new drug discovery through similarity learning from drug-target joint feature spaces

Additional file 3 ∙ Table S1: AUC/Precision/recall/F1-Score values of four classical classifiers when using reliable, pairwise or randomly generated negative samples.∙ Table S2: 1094 drugs researched in this work.∙ Table S3: 1556 targets researched in this work.∙ Table S4: 11,819 validated drug-target interactions.

补充材料3 ∙ 表S1：采用可靠样本、成对样本或随机生成负样本时，四种经典分类器的AUC（受试者工作特征曲线下面积，Area Under Curve）、精确率（Precision）、召回率（Recall）与F1分数（F1-Score）数值。∙ 表S2：本研究涉及的1094种药物。∙ 表S3：本研究涉及的1556个靶点。∙ 表S4：经验证的11,819条药物-靶点相互作用数据。